Sciweavers

28 search results - page 1 / 6
» Incremental HMM Alignment for MT System Combination
Sort
View
ACL
2009
13 years 1 months ago
Incremental HMM Alignment for MT System Combination
Inspired by the incremental TER alignment, we re-designed the Indirect HMM (IHMM) alignment, which is one of the best hypothesis alignment methods for conventional MT system combi...
Chi-Ho Li, Xiaodong He, Yupeng Liu, Ning Xi
AMTA
2004
Springer
13 years 9 months ago
Multi-align: Combining Linguistic and Statistical Techniques to Improve Alignments for Adaptable MT
Abstract. An adaptable statistical or hybrid MT system relies heavily on the quality of word-level alignments of real-world data. Statistical alignment approaches provide a reasona...
Necip Fazil Ayan, Bonnie J. Dorr, Nizar Habash
EMNLP
2010
13 years 1 months ago
Combining Unsupervised and Supervised Alignments for MT: An Empirical Study
Word alignment plays a central role in statistical MT (SMT) since almost all SMT systems extract translation rules from word aligned parallel training data. While most SMT systems...
Jinxi Xu, Antti-Veikko I. Rosti
ACL
2007
13 years 5 months ago
Tailoring Word Alignments to Syntactic Machine Translation
Extracting tree transducer rules for syntactic MT systems can be hindered by word alignment errors that violate syntactic correspondences. We propose a novel model for unsupervise...
John DeNero, Dan Klein
ACL
2009
13 years 1 months ago
A Comparative Study of Hypothesis Alignment and its Improvement for Machine Translation System Combination
Recently confusion network decoding shows the best performance in combining outputs from multiple machine translation (MT) systems. However, overcoming different word orders prese...
Boxing Chen, Min Zhang, Haizhou Li, AiTi Aw